AI Radio FM - 深入剖析MOONCAKE:为Kimi提供动力的LLM服务平台 episode artwork

EPISODE · Mar 3, 2025 · 5 MIN

AI Radio FM - 深入剖析MOONCAKE:为Kimi提供动力的LLM服务平台

from AI Podcast · host weedge

本期播客深入探讨了Moonshot AI开发的LLM聊天机器人服务Kimi背后的服务平台MOONCAKE。MOONCAKE采用以KVCache为中心的解耦架构,不仅分离了预填充和解码集群,还高效利用GPU集群中未充分利用的CPU、DRAM、SSD和NIC资源,建立了分布式KVCache。该架构的核心是其以KVCache为中心的全局缓存和调度器,旨在最大化吞吐量,同时遵守严格的延迟相关服务水平目标(SLO)。

Episode metadata supplied by the publisher feed · Published Mar 3, 2025

Embed this episode

Ready to play

AI Radio FM - 深入剖析MOONCAKE:为Kimi提供动力的LLM服务平台

0:00 5:34

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of AI Podcast?

This episode is 5 minutes long.

When was this AI Podcast episode published?

This episode was published on March 3, 2025.

Can I download this AI Podcast episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!